aistplusplus_api
BlenderProc
| aistplusplus_api | BlenderProc | |
|---|---|---|
| 1 | 15 | |
| 333 | 2,544 | |
| 0.3% | 1.9% | |
| 0.0 | 8.3 | |
| about 1 year ago | 16 days ago | |
| Python | Python | |
| Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
aistplusplus_api
-
From Google, USC, and Berkeley researchers: 3D dance generation conditioned on music!
Github for Dataset: https://github.com/google/aistplusplus_api
BlenderProc
-
Synthetic image Generation
Blender with add-ons (Kubric, BlenderProc)
-
dataset collection for transfer learning
If you are interested, there are open source solutions on top of Unity, Blender, Unreal. You can generate yourself the data you described easier than it looks (the amount of options and settings can be intimidating with these tools).
-
Are there any tools to generate images and labels from 3d models/games?
Blender addons like https://github.com/google-research/kubric and https://github.com/DLR-RM/BlenderProc
- How to get started with synthetic data generation?
-
Course/Learning Material recommendations for getting started with Synthetic Data Generation for Computer Vision Models
I have been going through some papers and reviewing existing methods and I've come across stuff like UnrealCV (https://unrealcv.org/) and blenderproc (https://github.com/DLR-RM/BlenderProc).
-
Searching for MIT CSAIL's IKEA dataset
I'm trying to use BlenderProc to automatically generate training data for object recognition.
- [P] BlenderProc2: Photorealistic Rendering of Procedurally Generated Scenes
-
[D] What's the best method to generate synthetic data for an image with text? Small dataset
Check this out https://github.com/DLR-RM/BlenderProc. I haven't used it extensively, but it seems to decent for generating synthetic image data.
- Apple’s Machine Learning Team Introduces ‘Hypersim’: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
-
Using Blender for Computer Vision
That looks really interesting, have you seen BlenderProc: https://github.com/DLR-RM/BlenderProc it looks really similar just that BlenderProc already supports a vast variety of datasets and is fully documented.
What are some alternatives?
ICON - [CVPR'22] ICON: Implicit Clothed humans Obtained from Normals
zpy - Synthetic data for computer vision. An open source toolkit using Blender and Python.
tsdf-fusion-python - Python code to fuse multiple RGB-D images into a TSDF voxel volume.
albumentations - Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Meshroom - 3D Reconstruction Software
com.unity.perception - Perception toolkit for sim2real training and validation in Unity
segmentation_models.pytorch - Segmentation models with pretrained backbones. PyTorch.
agi2nerf - Simple tool for converting Agisoft XML files to NERF JSON files for https://github.com/NVlabs/instant-ngp
segmentation_models - Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
SingleViewReconstruction - Official Code: 3D Scene Reconstruction from a Single Viewport
medicaldetectiontoolkit - The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
kubric - A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.